{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper — Channel & Video Subtitles", "description": "Scrape full transcripts, timestamped segments, and subtitles from YouTube channels, playlists, and single videos. Pure HTTP Innertube engine, zero headless browser, ultra-fast, multi-language & translation support.", "version": "1.9", "x-build-id": "yN7dxF0hNbhuu6TWn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datasiphon~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datasiphon-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datasiphon~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-datasiphon-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datasiphon~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-datasiphon-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "targetType": { "title": "What are you sharing?", "enum": [ "auto", "channel", "playlist", "video" ], "type": "string", "description": "Pick what your links point to. \"Auto-detect\" figures it out from each URL (recommended). Force a type only if YouTube serves an unexpected page shape.", "default": "auto" }, "startUrls": { "title": "YouTube URLs", "type": "array", "description": "Paste one or more YouTube links. Mixing channels, playlists, and videos in one run is fine. Accepted formats: youtube.com/@handle, /channel/UC..., /c/Name, /user/Name, /playlist?list=..., /watch?v=..., youtu.be/..., /shorts/..., /live/..., /embed/..., or a bare 11-character video ID. Duplicates across links are scraped once.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxVideosPerUrl": { "title": "Max videos per link (0 = all)", "minimum": 0, "type": "integer", "description": "Hard cap per link: 0 scrapes every single video on the channel/playlist (can be thousands). A channel's total = its curated Videos tab + all Shorts + all streams + anything else in its uploads; you always get the complete set.", "default": 100 }, "startDate": { "title": "Only videos published from (optional)", "type": "string", "description": "Skip videos published before this date (YYYY-MM-DD, UTC). Leave empty for no lower bound. Dates come from video metadata where available.", "default": "" }, "endDate": { "title": "Only videos published until (optional)", "type": "string", "description": "Skip videos published after this date (YYYY-MM-DD, UTC). Leave empty for no upper bound. Videos with unknown dates are always kept, never dropped.", "default": "" }, "includeShorts": { "title": "Include Shorts", "type": "boolean", "description": "Also scrape YouTube Shorts found on the channel. They are always included if they appear in the uploads playlist.", "default": true }, "includeLiveStreams": { "title": "Include past live streams", "type": "boolean", "description": "Also scrape completed live streams (VODs) from the channel's Streams tab.", "default": true }, "preferredLanguages": { "title": "Preferred languages (in order)", "type": "array", "description": "ISO codes tried in order (e.g. en, es, de). The best available track is chosen: manual captions always beat auto-generated for the same language. If none match, the original language is returned and availableLanguages in the output shows every option YouTube has.", "default": [ "en" ], "items": { "type": "string" } }, "preferAutoGenerated": { "title": "Allow auto-generated captions", "type": "boolean", "description": "When a video has no human-made subtitles, fall back to YouTube's automatic speech recognition. Turning this off will mark caption-less videos as NO_TRANSCRIPT_AVAILABLE instead.", "default": true }, "translateTo": { "title": "Translate transcripts to (optional)", "type": "string", "description": "ISO code of the language you want everything in (e.g. es, fr, de). Uses YouTube's server-side translation. Leave empty to keep the original language. isTranslation: true in the output marks translated items.", "default": "" }, "outputFormats": { "title": "Output format detail", "enum": [ "all", "plainTextOnly", "segmentsOnly", "srtOnly" ], "type": "string", "description": "Which transcript shapes to write into each dataset item.", "default": "all" }, "fetchVideoMetadata": { "title": "Fetch video metadata", "type": "boolean", "description": "Enrich each item with description, view count, publish date, thumbnail, keywords, category, and all available caption languages. Disable for maximum speed on huge channels.", "default": true }, "generateChannelSummaryFile": { "title": "Also save one combined Markdown file per channel", "type": "boolean", "description": "Writes TRANSCRIPTS_.md into the Key-Value store: a table of contents plus every transcript in one document. Handy for humans and for importing into Notion/Obsidian.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Strongly recommended: Apify Proxy. YouTube rate-limits datacenter IPs aggressively — without a proxy, large channels often fail with IP_BLOCKED. For channels with 100+ videos, RESIDENTIAL proxies give the best results.", "default": { "useApifyProxy": true } }, "maxConcurrency": { "title": "Parallel videos", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many videos to fetch simultaneously (1–50). Higher is faster; 10 is a safe default. If you see IP_BLOCKED statuses, lower this and/or add residential proxies.", "default": 10 }, "fallbackProxyConfiguration": { "title": "Fallback proxy (used only for blocked videos)", "type": "object", "description": "Cheap proxy is tried first; videos YouTube blocks are retried through this proxy. Default: Apify Residential. Set to null to disable.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "maxCacheAgeDays": { "title": "Max cache age (days)", "minimum": 0, "maximum": 365, "type": "integer", "description": "Transcripts fetched within this many days are returned from the cache (faster, no proxy). Rows show cached, fetched_at and cacheAgeDays. Set 0 to always fetch fresh.", "default": 90 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }